© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6948
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on instructions or code snippets that describe selecting a child <img> element and reading its src attribute.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .↵
    -0.07
     Freem
    -0.07
     オ
    -0.07
     Microsoft
    -0.07
    ใหญ
    -0.06
     H
    -0.06
    PFN
    -0.06
     k
    -0.06
     packaged
    -0.06
     CV
    -0.06
    POSITIVE LOGITS
     detain
    0.06
    	EIF
    0.06
     detainees
    0.06
     phận
    0.06
     державного
    0.06
     یه
    0.06
    ní
    0.06
    ">{
    0.06
     /////
    0.06
    '];
    ↵
    0.06
    Activations Density 0.166%

    No Known Activations